Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
Author:
Ha Minh-Khue1ORCID, Phan Thien-Luan12ORCID, Nguyen Duc3, Quan Nguyen1, Ha-Phan Ngoc-Quan4ORCID, Ching Congo2, Hieu Nguyen1
Affiliation:
1. Department of Physics and Electronic Engineering, University of Science, Vietnam National University of Ho Chi Minh City, Ho Chi Minh City 70000, Vietnam 2. Graduate Institute of Biomedical Engineering, National Chung Hsing University, Taichung 402, Taiwan 3. Faculty of Information Technology, University of Science, Vietnam National University of Ho Chi Minh City, Ho Chi Minh City 70000, Vietnam 4. Independent Researcher, Ho Chi Minh City 70000, Vietnam
Abstract
Artificial intelligence (AI) radar technology offers several advantages over other technologies, including low cost, privacy assurance, high accuracy, and environmental resilience. One challenge faced by AI radar technology is the high cost of equipment and the lack of radar datasets for deep-learning model training. Moreover, conventional radar signal processing methods have the obstacles of poor resolution or complex computation. Therefore, this paper discusses an innovative approach in the integration of radar technology and machine learning for effective surveillance systems that can surpass the aforementioned limitations. This approach is detailed into three steps: signal acquisition, signal processing, and feature-based classification. A hardware prototype of the signal acquisition circuitry was designed for a Continuous Wave (CW) K-24 GHz frequency band radar sensor. The collected radar motion data was categorized into non-human motion, human walking, and human walking without arm swing. Three signal processing techniques, namely short-time Fourier transform (STFT), mel spectrogram, and mel frequency cepstral coefficients (MFCCs), were employed. The latter two are typically used for audio processing, but in this study, they were proposed to obtain micro-Doppler spectrograms for all motion data. The obtained micro-Doppler spectrograms were then fed to a simplified 2D convolutional neural networks (CNNs) architecture for feature extraction and classification. Additionally, artificial neural networks (ANNs) and 1D CNN models were implemented for comparative analysis on various aspects. The experimental results demonstrated that the 2D CNN model trained on the MFCC feature outperformed the other two methods. The accuracy rate of the object classification models trained on micro-Doppler features was 97.93%, indicating the effectiveness of the proposed approach.
Funder
University of Science, VNU-HCM National Science and Technology Council
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference41 articles.
1. A Review of Video Surveillance Systems;Elharrouss;J. Vis. Commun. Image Represent.,2021 2. Perra, C., Kumar, A., Losito, M., Pirino, P., Moradpour, M., and Gatto, G. (2021). Monitoring Indoor People Presence in Buildings Using Low-Cost Infrared Sensor Array in Doorways. Sensors, 21. 3. Design and Implementation of an Embedded Home Surveillance System by Use of Multiple Ultrasonic Sensors;Bai;IEEE Trans. Consum. Electron.,2010 4. Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks;Elkelany;IEEE Sens. J.,2021 5. A Comprehensive Survey of Privacy-Preserving Federated Learning: A Taxonomy, Review, and Future Directions;Yin;ACM Comput. Surv.,2021
|
|